Update README.md

README.md

@@ -42,18 +42,27 @@ GRM-2.6-Plus already punches well above its weight class for a 27B model — com
 ## Usage
 
 ```python
-from openai import OpenAI
+from vllm import LLM, SamplingParams
 
-client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
-
-response = client.chat.completions.create(
-    model="morikomorizz/GRM-2.6-Plus-Primal",
-    messages=[{"role": "user", "content": "Your prompt here"}],
-    max_tokens=81920,
+# Parameter liar yang kau inginkan, tanpa disembunyikan di 'extra_body'
+sampling_params = SamplingParams(
     temperature=1.0,
     top_p=0.95,
-    extra_body={"top_k": 20},
+    top_k=20,
+    max_tokens=81920
 )
-print(response.choices[0].message.content)
+
+# Memuat model Primal kebanggaanmu secara langsung ke memori
+llm = LLM(model="morikomorizz/GRM-2.6-Plus-Primal")
+
+# Percakapan mentahmu
+messages = [{"role": "user", "content": "Your prompt here"}]
+
+# Memerintahkan entitas untuk merespons
+outputs = llm.chat(messages, sampling_params=sampling_params)
+
+# Menikmati hasilnya
+for output in outputs:
+    print(output.outputs[0].text)
 ```
 *Based on [OrionLLM/GRM-2.6-Plus](https://huggingface.co/OrionLLM/GRM-2.6-Plus) · Architecture: Qwen3.6-27B · Tensor type: BF16*